AI RESEARCH
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models
arXiv CS.CV
•
ArXi:2506.19300v2 Announce Type: replace Open-Vocabulary Camouflaged Object Segmentation (OVCOS) seeks to segment and classify camouflaged objects from arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories. Recent approaches typically adopt a two-stage paradigm: first segmenting objects, then classifying the segmented regions using Vision Language Models (VLMs). However, these methods (1) suffer from a domain gap caused by the mismatch between VLMs' full-image